Cheng(Kit) CHEN

Hi @iChiaGuo , the crash of the conversion from Tensorflow mobilenet to caffe is a known issue, you can refer the [test](https://github.com/Microsoft/MMdnn/blob/cfd779c523dea97f794fe6e9a0038e1befbb0996/tests/test_conversion_imagenet.py#L878) to get it. And we have no idea...

Slice layer of Caffe parser is not implemented. We will inform you asap. Thanks.

Hi @felix-tracxpoint , the problem is, image preprocessing is a part of your model, whose operators are not implemented in our TensorFlow parser. I can try to ignore these layer...

@namizzz We could skip these layers (with .real_name) or reset the input node to convert this model.

You can try the general converter [MMdnn](https://github.com/Microsoft/MMdnn), which supports both py2 and py3.

@shresthamalik Try to install a caffe instead of the pure protobuf implementation.